maxime and Claude Opus 5.5
0abba2d0ed
Label keys start/end/family in the bench and the docs (benchmark unchanged); knowledge path in data.py
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 12:40:03 +01:00
maxime and Claude Opus 5.5
3ea6b3e419
improve: S1
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 11:56:56 +01:00
maxime and Claude Opus 5.5
5438b0b469
wf-improve: S2
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-14 15:03:02 +01:00
maxime and Claude Opus 5.5
7e3043d3a0
wf-improve: S1
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-14 14:59:41 +01:00
maxime and Claude Opus 5.5
21a35d90aa
Optimizer, second user of the contract (categories, scripts/data.py); labels and data from the labeling and aimsight-data repositories
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-13 17:01:14 +01:00
maxime and Claude Opus 5.5
388619685a
Review fixes; README and CLAUDE.md finalised
...
- cancel reverts only the run's commits (base..HEAD), never the caller's edits
- validator diffs base..HEAD, not the working tree
- fix commits carry their Co-Authored-By line; no redundant end benchmark
- score.py: clear error on a missing labels file; docstring says end is not passed
- usage lines; README and CLAUDE.md for the generic workflow
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-13 12:45:14 +01:00
maxime and Claude Opus 5.5
0de006bcb2
wf-improve generic: the caller gives the range, labels, reference truth, families, context and output folder
...
Skill and agents no longer name Diagnostic-app paths (analyses, labeling/auto,
demande.json, summary location, git rules of the working repository).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-13 12:40:30 +01:00
maxime and Claude Opus 5.5
80e00a4898
wf-improve tools in skills/wf-improve/scripts/
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-13 12:31:22 +01:00
maxime and Claude Opus 5.5
6df274f580
Skill learner -> wf-improve (/detectors:wf-improve); scripts/wf-improve/, sessions in wf-improve/
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-13 12:26:02 +01:00
maxime and Claude Opus 5.5
969637499f
Detectors in English, under scripts/; learner tools under scripts/learner/
...
- data.py (was donnees.py): unused filtrer, heure_image and image sorting removed
- score.py: dead functions (validite, marquer, detectes, score, familles) and the
validity levels removed; --from/--to
- regression.py: history.csv and --seance/--etape removed
- categories.py: --from/--to/--chunk/--history; process values images/none/check
- benchmark on all stations unchanged (same 132 figures)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-13 12:19:52 +01:00